# Derandomized knockoffs: leveraging e-values for false discovery rate control

arXiv: https://arxiv.org/abs/2205.15461 · HTML: https://mlsanity.com/paper/2205.15461/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 May 2022.

## Built on by (most cited first, 12 of 12)

- [Derandomized Novelty Detection with FDR Control via Conformal E-values](https://mlsanity.com/paper/2302.07294/) (2023)
- [Model-X Sequential Testing for Conditional Independence via Testing by Betting](https://mlsanity.com/paper/2210.00354/) (2022)
- [Online multiple testing with e-values](https://mlsanity.com/paper/2311.06412/) (2023)
- [Combining Evidence Across Filtrations](https://mlsanity.com/paper/2402.09698/) (2024)
- [Leave-One-Out Stable Conformal Prediction](https://mlsanity.com/paper/2504.12189/) (2025)
- [A Conditional Distribution Equality Testing Framework using Deep Generative Learning](https://mlsanity.com/paper/2509.17729/) (2025)
- [ARK: Robust Knockoffs Inference with Coupling](https://mlsanity.com/paper/2307.04400/) (2023)
- [Data-light Uncertainty Set Merging with Admissibility](https://mlsanity.com/paper/2410.12201/) (2024)
- [False Discovery Rate Control via Frequentist-assisted Horseshoe](https://mlsanity.com/paper/2502.05460/) (2025)
- [Knockoff-Guided Compressive Sensing: A Statistical Machine Learning Framework for Support-Assured Signal Recovery](https://mlsanity.com/paper/2505.24727/) (2025)
- [GRIP2: A Robust and Powerful Deep Knockoff Method for Feature Selection](https://mlsanity.com/paper/2602.00218/) (2026)
- [Virtual Dummies: Enabling Scalable FDR-Controlled Variable Selection via Sequential Sampling of Null Features](https://mlsanity.com/paper/2604.07464/) (2026)

## Abstract (arXiv)

Model-X knockoffs is a flexible wrapper method for high-dimensional regression algorithms, which provides guaranteed control of the false discovery rate (FDR). Due to the randomness inherent to the method, different runs of model-X knockoffs on the same dataset often result in different sets of selected variables, which is undesirable in practice. In this paper, we introduce a methodology for derandomizing model-X knockoffs with provable FDR control. The key insight of our proposed method lies in the discovery that the knockoffs procedure is in essence an e-BH procedure. We make use of this connection, and derandomize model-X knockoffs by aggregating the e-values resulting from multiple knockoff realizations. We prove that the derandomized procedure controls the FDR at the desired level, without any additional conditions (in contrast, previously proposed methods for derandomization are not able to guarantee FDR control). The proposed method is evaluated with numerical experiments, where we find that the derandomized procedure achieves comparable power and dramatically decreased selection variability when compared with model-X knockoffs.